Search results for " Image processing"
showing 10 items of 2323 documents
A Neural Network Meta-Model and its Application for Manufacturing
2015
International audience; Manufacturing generates a vast amount of data both from operations and simulation. Extracting appropriate information from this data can provide insights to increase a manufacturer's competitive advantage through improved sustainability, productivity, and flexibility of their operations. Manufacturers, as well as other industries, have successfully applied a promising statistical learning technique, called neural networks (NNs), to extract meaningful information from large data sets, so called big data. However, the application of NN to manufacturing problems remains limited because it involves the specialized skills of a data scientist. This paper introduces an appr…
Bridging Sensing and Decision Making in Ambient Intelligence Environments
2009
Context-aware and Ambient Intelligence environments represent one of the emerging issues in the last decade. In such intelligent environments, information is gathered to provide, on one hand, autonomic and easy to manage applications, and, on the other, secured access controlled environments. Several approaches have been defined in the literature to describe context-aware application with techniques to capture and represent information related to a specified domain. However and to the best of our knowledge, none has questioned the reliability of the techniques used to extract meaningful knowledge needed for decision making especially if the information captured is of multimedia types (image…
Incorporating depth information into few-shot semantic segmentation
2021
International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…
Unsupervised learning of category-specific symmetric 3D keypoints from point sets
2020
Lecture Notes in Computer Science, 12370
Enhancing scientific information systems with semantic annotations
2013
International audience; Scientific Information Systems aim to produce or improve knowledge on a subject through activities of research and development. The management of scientific dat a requires some essential properties. We propose SemLab an architecture that sup ports interoperability, data quality and extensibility through a unique paradigm: semantic annotation. We present two app lications that validate our architecture.
Representing and Reasoning for Spatiotemporal Ontology Integration
2004
International audience; The World-Wide Web hosts many autonomous and heterogeneous information sources. In the near future each source may be described by its own ontology. The distributed nature of ontology development will lead to a large number of local ontologies covering overlapping domains. Ontology integration will then become an essential capability for effective interoperability and information sharing. Integration is known to be a hard problem, whose complexity increases particularly in the presence of spatiotemporal information. Space and time entail additional problems such as the heterogeneity of granularity used in representing spatial and temporal features. Spatio-temporal ob…
Improving Video Object Detection by Seq-Bbox Matching
2019
International audience
Event-Based Trajectory Prediction Using Spiking Neural Networks
2021
International audience; In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory…
Some Computational Aspects of DISTANCE-SAT
2007
In many AI fields, one must face the problem of finding a solution that is as close as possible to a given configuration. This paper addresses this problem in a propositional framework. We introduce the decision problem distance-sat, which consists in determining whether a propositional formula admits a model that disagrees with a given partial interpretation on at most d variables. The complexity of distance-sat and of several restrictions of it are identified. Two algorithms based on the well-known Davis/Logemann/Loveland search procedure for the satisfiability problem sat are presented so as to solve distance-sat for CNF formulas. Their computational behaviors are compared with the ones …
How to Enrich Description Logics with Fuzziness
2017
International audience; The paper describes the relation between fuzzy and non-fuzzy description logics. It gives an overview about current research in these areas and describes the difference between tasks for description logics and fuzzy logics. The paper also deals with the transformation properties of description logics to fuzzy logics and backwards. While the process of transformation from a description logic to a fuzzy logic is a trivial inclusion, the other way of reducing information from fuzzy logic to description logic is a difficult task, that will be topic of future work.